Papers by Paul Roit

8 papers
Asking It All: Generating Contextualized Questions for any Semantic Role (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to question generation require conditioning on existing answers in text . previous work required human-curated templates, limiting coverage and question fluency .
Approach: They propose a task of role question generation that produces a prototype and revises it to be contextually appropriate for the passage.
Outcome: The proposed model generates diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles.
LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models (2022.emnlp-demos)

Copied to clipboard

Challenge: Transformer-based language models (LMs) are opaque and unexplained, causing problems for endusers and developers who wish to debug or fix their behaviour.
Approach: They propose an interactive debugger tool for transformer-based LMs that provides a fine-grained interpretation of the model's internal prediction process and a powerful framework for intervening in LM behavior.
Outcome: The proposed tool provides a fine-grained interpretation of the model's internal prediction construction process, and a powerful framework for intervening in LM behavior.
Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback (2023.acl-long)

Copied to clipboard

Challenge: Recent advances in abstractive summarization systems produce factually inconsistent text . this is emphasized in tasks like summarizing, which often produce inconsistent text with no input article .
Approach: They use reinforcement learning to optimize for factual consistency and explore trade-offs . they use textual-entailment rewards to optimize the accuracy of the generated summaries .
Outcome: The proposed method improves faithfulness, salience and conciseness of the generated summaries.
QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to consolidate textual inputs are difficult to implement . a recent study aims to capture content overlap by combining multiple textual elements .
Approach: They propose to align predicate-argument relations across texts to represent content overlap . their setting exploits QA-SRL, utilizing question-answer pairs to capture predicates .
Outcome: The proposed task captures content overlap beyond lexical similarity and complements cross-document coreference with proposition-level links, offering potential use for downstream tasks.
Controlled Text Reduction (2022.emnlp-main)

Copied to clipboard

Challenge: Abstractive text summarization models separate the salience detection phase from the text generation phase.
Approach: They propose to formalize Controlled Text Reduction as a standalone task . they advocate the potential of such models for modular fully-automatic summarization .
Outcome: The proposed model shows that it is possible to produce a reduced version of a source text using decomposed modeling.
Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations (2022.naacl-main)

Copied to clipboard

Challenge: Existing datasets for sentence fusion tasks are limited in size and scope . despite recent advances, cross-document tasks such as multi-document summarization have not progressed with the same pace.
Approach: They propose to extend a sentence fusion dataset by almost four times its original size . they relabel the dataset and employ more data sources to improve model performance .
Outcome: The proposed dataset triples the size of an earlier dataset and improves performance . it also includes more complex training instances better reflecting those found in "the wild"
Controlled Crowdsourcing for High-Quality QA-SRL Annotation (2020.acl-main)

Copied to clipboard

Challenge: Question-answer driven Semantic Role Labeling (QA-SRL) is an open and natural flavour of SRL, potentially attainable from laymen.
Approach: They propose a question-answer driven semantic role labeling approach that uses question-announced questions to label predicate-argument relationships.
Outcome: The proposed method yields high-quality annotation with dramatically higher coverage, enabling future replicable research of natural semantic annotations.
Localizing Factual Inconsistencies in Attributable Text Generation (2026.tacl-1)

Copied to clipboard

Challenge: Existing methods for detecting hallucinations in model-generated texts fail to pinpoint errors.
Approach: They propose a formalism for localizing factual inconsistencies in attributable text generation . they propose to decompose the generated text into simple question-answer pairs .
Outcome: The proposed method achieves substantial inter-annotator agreement while achieving a substantial consistency score.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations